CN114882699B - Road section traffic risk identification method based on conflict space-time correlation characteristics in area - Google Patents
Road section traffic risk identification method based on conflict space-time correlation characteristics in area Download PDFInfo
- Publication number
- CN114882699B CN114882699B CN202210366574.5A CN202210366574A CN114882699B CN 114882699 B CN114882699 B CN 114882699B CN 202210366574 A CN202210366574 A CN 202210366574A CN 114882699 B CN114882699 B CN 114882699B
- Authority
- CN
- China
- Prior art keywords
- traffic
- conflicts
- time
- conflict
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 17
- 230000003993 interaction Effects 0.000 claims abstract description 8
- 230000008447 perception Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 206010039203 Road traffic accident Diseases 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
本发明公开了一种基于区域内冲突时空关联特征的路段交通风险辨识方法，包括步骤：获取路侧精细感知的实时交通目标数据；基于每一帧的精细感知的实时交通目标数据，定义每一帧与目标车辆有交互的周边目标，并计算每个目标车辆与周边目标发生交通冲突相关的参数；根据计算的发生交通冲突相关的参数，定义每一帧车辆交互产生的交通冲突识别指标TDTC，每个冲突的位置，时间间隔；构建一段时间内区域冲突的时空关联风险系数模型，用于识别冲突在时空上的关联程度；根据时空关联风险系数模型计算一定时空范围内冲突的关联程度，并对该区域冲突的严重程度进行判断，进而确定路段是否有交通运行风险。本发明可提高交通风险辨识准确性。
The invention discloses a traffic risk identification method for road sections based on temporal-spatial correlation characteristics of intra-area conflicts, comprising the steps of: obtaining fine-sensed real-time traffic target data on the roadside; defining surrounding targets that interact with target vehicles in each frame based on the finely-sensed real-time traffic target data of each frame, and calculating parameters related to traffic conflicts between each target vehicle and surrounding targets; defining traffic conflict identification indicators TDTC generated by vehicle interaction in each frame, the location of each conflict, and time interval according to the calculated parameters related to traffic conflicts in each frame; The correlation degree of conflict in time and space; calculate the correlation degree of conflict in a certain space-time range according to the spatio-temporal correlation risk coefficient model, and judge the severity of the conflict in the area, and then determine whether there is traffic operation risk in the road section. The invention can improve the accuracy of traffic risk identification.
Description
技术领域technical field
本发明涉及交通安全管理领域，具体涉及一种基于区域内冲突时空关联特征的路段交通风险辨识方法及系统。The invention relates to the field of traffic safety management, in particular to a traffic risk identification method and system for road sections based on temporal-spatial correlation characteristics of intra-area conflicts.
背景技术Background technique
随着我国经济的发展和交通运输量的持续增加，道路交通中的安全问题也在日益凸显。交通安全成为当前急需解决的问题，而在交通事故发生之前，如果能够对交通事故征兆提前辨识，识别可能演化为交通事故的严重冲突，则有可能给驾驶人做出预警或加强主动交通控制，会有效减少交通事故的发生。With the development of our country's economy and the continuous increase of traffic volume, the safety problems in road traffic are becoming increasingly prominent. Traffic safety has become an urgent problem to be solved at present, and before traffic accidents, if the signs of traffic accidents can be identified in advance, and serious conflicts that may evolve into traffic accidents can be identified, it is possible to give early warning to drivers or strengthen active traffic control, which will effectively reduce the occurrence of traffic accidents.
交通冲突是指在可观测的条件下，2个或2个以上交通参与者在空间和时间上相互接近，以至于如果其中任何一方不改变其行驶轨迹，将会有发生碰撞的风险。当前国内外对交通冲突的衡量指标并不统一，且对于区分冲突风险等级的指标阈值也存在多种不同的划分标准。而不同冲突指标值情况下冲突演化成为事故的概率也不相同。Traffic conflict means that under observable conditions, two or more traffic participants are close to each other in space and time, so that if any of them does not change its driving trajectory, there will be a risk of collision. At present, the measurement indicators of traffic conflicts at home and abroad are not unified, and there are many different division standards for the index thresholds that distinguish the conflict risk levels. However, the probability of conflict evolving into an accident is different under different conflict index values.
目前，现有技术中主要集中于对两车的交通冲突研究，针对多车关联冲突的研究相对较少，而多车冲突在很短的时间内、很小的范围内交互影响，则演变为交通事故的可能性更大，且更严重。At present, the existing technology mainly focuses on the research of traffic conflicts between two vehicles, and there are relatively few studies on multi-vehicle related conflicts. However, multi-vehicle conflicts interact with each other in a short period of time and within a small range, and the possibility of evolving into traffic accidents is greater and more serious.
发明内容Contents of the invention
本发明主要目的在于提出一种基于区域内冲突时空关联特征的路段交通风险辨识方法，该方法将一定区域范围内检测的冲突进行时空关联，识别与交通风险高度相关的冲突时空规律，以提高交通风险辨识准确性。The main purpose of the present invention is to propose a road section traffic risk identification method based on the spatio-temporal correlation characteristics of conflicts in the region. The method correlates the conflicts detected in a certain area in time and space, and identifies the spatio-temporal laws of conflicts highly related to traffic risks, so as to improve the accuracy of traffic risk identification.
本发明所采用的技术方案是：The technical scheme adopted in the present invention is:
提供一种基于区域内冲突时空关联特征的路段交通风险辨识方法，包括以下步骤：A traffic risk identification method for road sections based on temporal-spatial correlation characteristics of conflicts in the region is provided, which includes the following steps:
S1、获取路侧精细感知的实时交通目标数据，数据形式上至少包含每一帧所提取交通目标的横向坐标、纵向坐标、横向速度、纵向速度，时间戳；S1. Obtain the real-time traffic target data of roadside fine perception, and the data form at least includes the horizontal coordinates, vertical coordinates, horizontal speed, vertical speed, and time stamp of the traffic target extracted in each frame;
S2、基于每一帧的精细感知的实时交通目标数据，定义每一帧与目标车辆有交互的周边目标，并计算每个目标车辆与周边目标发生交通冲突相关的参数；S2. Based on the finely perceived real-time traffic target data of each frame, define the surrounding targets that interact with the target vehicle in each frame, and calculate the parameters related to the traffic conflict between each target vehicle and the surrounding targets;
S3、根据计算的发生交通冲突相关的参数，定义每一帧车辆交互产生的交通冲突识别指标TDTC，每个冲突的位置，时间间隔；TDTC定义为在某个时刻，假定交通参与者的速度和路径方向保持不变，2个参与者通过当前方向的冲突点的时间差；S3. According to the calculated parameters related to traffic conflicts, define the traffic conflict identification index TDTC generated by each frame of vehicle interaction, the position of each conflict, and the time interval; TDTC is defined as the time difference between two participants passing the conflict point in the current direction at a certain moment, assuming that the speed and path direction of the traffic participants remain unchanged;
S4、构建一段时间内区域冲突的时空关联风险系数模型，用于识别冲突在时空上的关联程度，该时空关联风险系数模型为：S4. Construct a spatiotemporal correlation risk coefficient model of regional conflicts for a period of time to identify the degree of spatiotemporal correlation of conflicts. The spatiotemporal correlation risk coefficient model is:
式中，t表示两次冲突发生的时间间隔；tT1表示时间上前一冲突的TDTC的倒数；tT2表示时间上后一冲突TDTC的倒数；s表示两次冲突发生位置的空间距离；In the formula, t represents the time interval between two conflicts; t T1 represents the reciprocal of the TDTC of the previous conflict in time; t T2 represents the reciprocal of the TDTC of the latter conflict in time; s represents the spatial distance of the two conflicts;
S5、根据时空关联风险系数模型计算一定时空范围内冲突的关联程度，并对该区域冲突的严重程度进行判断，进而确定路段是否有交通运行风险。S5. Calculate the correlation degree of conflicts in a certain space-time range according to the spatio-temporal correlation risk coefficient model, and judge the severity of the conflicts in the area, and then determine whether there is a traffic operation risk in the road section.
接上述技术方案，交通目标主要是机动车，实时交通目标数据来自路侧视频、微波雷达或者激光雷达路侧感知设备。Following the above technical solution, the traffic targets are mainly motor vehicles, and the real-time traffic target data comes from roadside video, microwave radar or lidar roadside sensing equipment.
接上述技术方案，两次冲突发生的时间间隔t为1～5s。Following the above technical solution, the time interval t between two collisions is 1-5s.
接上述技术方案，通过时间和空间距离来确定风险，将冲突分为不同等级。Continuing with the above technical solution, risks are determined through time and space distances, and conflicts are divided into different levels.
接上述技术方案，每一帧的精细感知的实时交通目标数据刷新频率不低于1Hz，不高于20Hz。Following the above technical solution, the refresh frequency of real-time traffic target data for each frame of fine perception is not lower than 1 Hz and not higher than 20 Hz.
接上述技术方案，每个目标车辆与周边目标发生交通冲突相关的参数包括相对位置、相对速度。Following the above technical solution, the parameters related to the traffic conflict between each target vehicle and surrounding targets include relative position and relative speed.
本发明还提供一种基于区域内冲突时空关联特征的路段交通风险辨识系统，包括：The present invention also provides a road segment traffic risk identification system based on the temporal-spatial correlation characteristics of conflicts in the region, including:
数据获取模块，用于获取路侧精细感知的实时交通目标数据，数据形式上至少包含每一帧所提取交通目标的横向坐标、纵向坐标、横向速度、纵向速度，时间戳；The data acquisition module is used to acquire the real-time traffic target data of roadside fine perception, and the data form at least includes the horizontal coordinates, vertical coordinates, horizontal speed, vertical speed and time stamp of the traffic target extracted in each frame;
计算模块，用于基于每一帧的精细感知的实时交通目标数据，定义每一帧与目标车辆有交互的周边目标，并计算每个目标车辆与周边目标发生交通冲突相关的参数；The calculation module is used to define the surrounding targets that interact with the target vehicle in each frame based on the finely perceived real-time traffic target data of each frame, and calculate the parameters related to the traffic conflict between each target vehicle and the surrounding targets;
冲突识别指标定义模块，用于根据计算的发生交通冲突相关的参数，定义每一帧车辆交互产生的交通冲突识别指标TDTC，每个冲突的位置，时间间隔；TDTC定义为在某个时刻，假定交通参与者的速度和路径方向保持不变，2个参与者通过当前方向的冲突点的时间差；The conflict identification index definition module is used to define the traffic conflict identification index TDTC generated by each frame of vehicle interaction according to the calculated parameters related to traffic conflicts, the position of each conflict, and the time interval; TDTC is defined as the time difference between two participants passing the conflict point in the current direction at a certain moment, assuming that the speed and path direction of the traffic participants remain unchanged;
系数模型构建模块，用于构建一段时间内区域冲突的时空关联风险系数模型，用于识别冲突在时空上的关联程度，该时空关联风险系数模型为：The coefficient model building block is used to construct a spatio-temporal correlation risk coefficient model of regional conflicts within a period of time, and is used to identify the correlation degree of conflicts in time and space. The spatio-temporal correlation risk coefficient model is:
式中，t表示两次冲突发生的时间间隔；tT1表示时间上前一冲突的TDTC的倒数；tT2表示时间上后一冲突TDTC的倒数；s表示两次冲突发生位置的空间距离；In the formula, t represents the time interval between two conflicts; t T1 represents the reciprocal of the TDTC of the previous conflict in time; t T2 represents the reciprocal of the TDTC of the latter conflict in time; s represents the spatial distance of the two conflicts;
风险判断模块，用于根据时空关联风险系数模型计算一定时空范围内冲突的关联程度，并对该区域冲突的严重程度进行判断，进而确定路段是否有交通运行风险。The risk judgment module is used to calculate the correlation degree of conflicts in a certain space-time range according to the time-space correlation risk coefficient model, and judge the severity of the conflicts in the area, and then determine whether there is a traffic operation risk in the road section.
接上述技术方案，该系统还包括风险等级划分模块，用于通过时间和空间距离来确定风险，将冲突分为不同等级。Following the above technical solution, the system also includes a risk level division module, which is used to determine risks through time and space distance, and divide conflicts into different levels.
接上述技术方案，每一帧的精细感知的实时交通目标数据刷新频率不低于1Hz，不高于20Hz。Following the above technical solution, the refresh frequency of real-time traffic target data for each frame of fine perception is not lower than 1 Hz and not higher than 20 Hz.
本发明还提供一种计算机存储介质，其内存储有可被处理器执行的计算机程序，该计算机程序执行上述技术方案基于区域内冲突时空关联特征的路段交通风险辨识方法。The present invention also provides a computer storage medium, which stores a computer program that can be executed by a processor, and the computer program executes the traffic risk identification method of the road section based on the temporal-spatial correlation characteristics of the conflict in the area of the above technical solution.
本发明产生的有益效果是：本发明创新性地从冲突的时空关联角度进行交通风险的辨识，基于路侧精细感知交通目标之间发生交通冲突相关的参数，并通过构建的区域冲突的时空关联风险系数模型计算该区域中的风险系数，将区域内关联冲突风险进行量化，对短时间窗内空间位置很近的两例冲突进行关联并划分严重程度，可提高交通风险辨识准确性。The beneficial effects produced by the present invention are: the present invention innovatively identifies traffic risks from the perspective of spatiotemporal association of conflicts, based on roadside fine perception of parameters related to traffic conflicts between traffic targets, and calculates the risk coefficient in the area through the constructed spatiotemporal association risk coefficient model of regional conflicts, quantifies the associated conflict risks in the area, associates and classifies the severity of two cases of conflicts with very close spatial positions in a short time window, and can improve the accuracy of traffic risk identification.
附图说明Description of drawings
下面将结合附图及实施例对本发明作进一步说明，附图中：The present invention will be further described below in conjunction with accompanying drawing and embodiment, in the accompanying drawing:
图1是本发明实施例基于区域内冲突时空关联特征的路段交通风险辨识方法的流程图；Fig. 1 is a flow chart of a road segment traffic risk identification method based on intra-area conflict spatio-temporal correlation characteristics according to an embodiment of the present invention;
图2为某时段内冲突发生前路段运行状态；Figure 2 shows the running status of the road section before the conflict occurred in a certain period of time;
图3为某时段内目标路段第一例交通冲突示意图；Fig. 3 is a schematic diagram of the first case of traffic conflict in the target road section in a certain period of time;
图4为某时段内目标路段第二例交通冲突示意图。Fig. 4 is a schematic diagram of the second example of traffic conflict on the target section within a certain period of time.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
如图1所示，本发明实施例基于区域内冲突时空关联特征的路段交通风险辨识方法主要包括以下步骤：As shown in Fig. 1, the embodiment of the present invention based on the intra-area conflict spatio-temporal correlation feature road segment traffic risk identification method mainly includes the following steps:
S1、获取路侧精细感知的实时交通目标数据，交通目标主要是机动车，数据来源不局限于视频、微波雷达、激光雷达路侧感知设备的哪一种；精细感知实时交通数据形式上至少包含每一帧所提取交通目标的横向坐标、纵向坐标、横向速度、纵向速度、时间戳；S1. Obtain the real-time traffic target data of roadside fine perception. The traffic target is mainly a motor vehicle, and the data source is not limited to video, microwave radar, and lidar roadside sensing equipment; the form of fine perception real-time traffic data includes at least the horizontal coordinates, vertical coordinates, horizontal speed, vertical speed, and time stamp of the traffic target extracted in each frame;
S2、基于上述每一帧的精细感知交通目标数据，定义每一帧与目标车辆有交互或无交互的周边目标，并计算每个目标车辆与周边目标发生交通冲突相关的参数；S2. Based on the above-mentioned finely perceived traffic target data of each frame, define the surrounding targets with or without interaction with the target vehicle in each frame, and calculate the parameters related to the traffic conflict between each target vehicle and the surrounding targets;
S3、根据计算的发生交通冲突相关的参数，如车辆之间的相对位置、相对速度等参数，定义每一帧车辆交互产生的交通冲突识别指标：TDTC(Time Difference toCollision)，每个冲突的位置(Cx,Cy)，时间t；TDTC定义为在某个时刻，假定交通参与者的速度和路径方向保持不变，2个参与者通过当前方向的冲突点的时间差；S3. According to the calculated parameters related to traffic conflicts, such as the relative position and relative speed between vehicles, define the traffic conflict identification index generated by vehicle interaction in each frame: TDTC (Time Difference to Collision), the position (Cx, Cy) of each conflict, time t; TDTC is defined as the time difference between two participants passing the conflict point in the current direction at a certain moment, assuming that the speed and path direction of the traffic participants remain unchanged;
S4、构建一段时间内区域冲突的时空关联风险系数模型，识别冲突在时空上的关联程度；这个时间间隔一般是1～5s；该时空关联风险系数模型为：S4. Construct a time-space correlation risk coefficient model of regional conflicts within a period of time to identify the degree of correlation of conflicts in time and space; this time interval is generally 1 to 5 seconds; the time-space correlation risk coefficient model is:
式中，t表示两次冲突发生的时间间隔；tT1表示时间上前一冲突的TDTC的倒数；tT2表示时间上后一冲突TDTC的倒数；s表示两次冲突发生位置的空间距离；由于各关联冲突的TDTC值越小，tT1和tT2值越大，冲突风险等级越高；冲突发生点的空间距离越接近，冲突风险等级越高；相关冲突发生的时间差越小，冲突风险等级越高。且经大量数据拟合分析，表示各冲突严重程度的tT1和tT2的乘积与风险系数的拟合关系呈线性；冲突时间差t与风险系数的拟合关系呈指数型；冲突发生位置的空间距离s风险系数的拟合关系呈反比，因此利用上述时空关联风险系数模型计算时空关联风险系数，可以提高交通风险辨识准确性。In the formula, t represents the time interval between two conflicts; t T1 represents the reciprocal of the TDTC of the previous conflict in time; t T2 represents the reciprocal of the TDTC of the latter conflict in time ; And after a large amount of data fitting analysis, the fitting relationship between the product of t T1 and t T2 representing the severity of each conflict and the risk coefficient is linear; the fitting relationship between the conflict time difference t and the risk coefficient is exponential; the spatial distance s of the conflict location The fitting relationship of the risk coefficient is inversely proportional. Therefore, using the above-mentioned spatio-temporal correlation risk coefficient model to calculate the spatio-temporal correlation risk coefficient can improve the accuracy of traffic risk identification.
S5、根据时空关联风险系数模型计算一定时空范围内冲突的关联程度，对该区域冲突的严重程度进行判断，进而确定路段是否有交通运行风险；S5. Calculate the correlation degree of conflicts in a certain space-time range according to the time-space correlation risk coefficient model, judge the severity of the conflicts in this area, and then determine whether there is a traffic operation risk in the road section;
步骤S1中，对路侧感知数据的来源不做限定，不局限于路侧视频、微波雷达、激光雷达的哪一种；但是规定所获取的数据结构上至少包含每一帧车辆目标的横向位置X、纵向位置Y、横向速度Vx、纵向速度Vy,以及时间戳t；要求的数据刷新频率不低于1Hz，一般不高于20Hz。In step S1, the source of roadside sensing data is not limited, not limited to roadside video, microwave radar, or lidar; however, it is stipulated that the acquired data structure at least includes the lateral position X, longitudinal position Y, lateral velocity Vx, longitudinal velocity Vy, and time stamp t of each frame of the vehicle target; the required data refresh frequency is not lower than 1 Hz, generally not higher than 20 Hz.
步骤S3中，根据上述目标车辆交互数据，获取交通冲突识别指标TDTC(TimeDifference to Collision)。同时通过记录每个交通冲突的时间t和冲突所处位置(Cx,Cy)。In step S3, a traffic conflict identification index TDTC (Time Difference to Collision) is obtained according to the target vehicle interaction data. At the same time by recording the time t of each traffic conflict and the location of the conflict (Cx, Cy).
通过时空关联风险系数R计算时空紧密程度，通过冲突在空间上的距离和时间的间隔来判断交通冲突之间的关联性，从而确定路段内区域关联冲突的严重性。The time-space tightness is calculated by the time-space correlation risk coefficient R, and the correlation between traffic conflicts is judged by the distance and time interval of conflicts in space, so as to determine the severity of regional correlation conflicts in the road section.
进一步地，可将区域关联冲突的严重性划分为不同等级。时间间隔选取5s内，通过时空关联风险系数R表示时空紧密程度，从而确定路段内区域关联冲突的严重性。路段时空关联风险严重程度判断标准为：R≤0.01，路段无时空关联风险；0.01＜R≤0.55，路段时空关联风险严重程度较低；0.55＜R≤2.55，路段时空关联风险严重程度为一般；2.55＜R≤13.55，路段时空关联风险严重程度为较严重；R＞13.55，路段时空关联风险严重程度为非常严重。Further, the severity of area association conflicts can be divided into different levels. The time interval is selected within 5s, and the spatio-temporal correlation risk coefficient R is used to represent the tightness of time and space, so as to determine the severity of regional correlation conflicts in the road section. The criteria for judging the severity of spatio-temporal correlation risk of a road section are: R≤0.01, no spatio-temporal correlation risk of the road section; 0.01<R≤0.55, low severity of spatio-temporal correlation risk of the road section; 0.55<R≤2.55, general spatio-temporal correlation risk severity of the road section; 2.55<R≤13.55, severe spatio-temporal correlation risk severity of the road section;
本发明的一个具体实施例中，提取某时段内目标路段两例交通冲突如图2，图3，该组冲突不同时间内位置分布如图4。In a specific embodiment of the present invention, two examples of traffic conflicts in the target section of a certain period of time are extracted as shown in Figure 2 and Figure 3, and the location distribution of the group of conflicts in different time periods is shown in Figure 4.
根据每个目标车辆与周边目标发生交通冲突相关的参数，可得第一例冲突tT1＝1.5s，冲突位置(1.70m，36.5m)，时间t1＝622s。According to the parameters related to the traffic conflict between each target vehicle and surrounding targets, the first conflict t T1 =1.5s, the conflict position (1.70m, 36.5m), and the time t 1 =622s can be obtained.
可得第二例冲突tT2＝1.2s，冲突位置(2.55m，40.3m)，时间t2＝625s。It can be obtained that the second conflict t T2 =1.2s, the conflict position (2.55m, 40.3m), and the time t 2 =625s.
将上述冲突数据代入时空关联风险系数公式计算可得R＝6.26。Substituting the above conflict data into the formula of the risk coefficient of space-time correlation can get R=6.26.
该案例时空关联风险系数为6.26，风险系数较大，因而该路段具有一定运行风险。In this case, the space-time correlation risk coefficient is 6.26, which is relatively large, so this road section has a certain operational risk.
本发明将区域内关联冲突风险进行量化，由区域关联风险系数模型，对短时间窗内空间位置很近的两例冲突进行关联并划分严重程度，可提高交通风险辨识准确性。此外该风险系数模型拟合效果好，且可较好地表示相关冲突自身严重程度、冲突时间差和冲突的空间距离与其关联风险间的关系，且经大量实测数据验证及修订，可较好地表示路段运行风险等级。The present invention quantifies the risks of associated conflicts in the region, and uses the regional associated risk coefficient model to associate and classify the severity of two cases of conflicts with very close spatial positions in a short time window, which can improve the accuracy of traffic risk identification. In addition, the risk coefficient model has a good fitting effect, and can better express the relationship between the severity of the relevant conflict itself, the time difference of the conflict, the spatial distance of the conflict and its associated risk, and has been verified and revised by a large number of measured data, and can better express the risk level of the road section operation.
本发明可适用于多种道路及车辆目标，较以往的交通冲突风险辨识技术应用对象更广泛。The invention can be applied to various roads and vehicle objects, and has wider application objects than the previous traffic conflict risk identification technology.
应当理解的是，对本领域普通技术人员来说，可以根据上述说明加以改进或变换，而所有这些改进和变换都应属于本发明所附权利要求的保护范围。It should be understood that those skilled in the art can make improvements or changes based on the above description, and all these improvements and changes should belong to the protection scope of the appended claims of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210366574.5A CN114882699B (en) | 2022-04-08 | 2022-04-08 | Road section traffic risk identification method based on conflict space-time correlation characteristics in area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210366574.5A CN114882699B (en) | 2022-04-08 | 2022-04-08 | Road section traffic risk identification method based on conflict space-time correlation characteristics in area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114882699A CN114882699A (en) | 2022-08-09 |
| CN114882699B true CN114882699B (en) | 2023-07-25 |
Family
ID=82670333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210366574.5A Active CN114882699B (en) | 2022-04-08 | 2022-04-08 | Road section traffic risk identification method based on conflict space-time correlation characteristics in area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114882699B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116434520B (en) * | 2023-02-01 | 2025-05-30 | 武汉理工大学 | A pedestrian crossing collision risk warning method and system based on holographic perception |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2693416A2 (en) * | 2012-07-31 | 2014-02-05 | Denso IT Laboratory, Inc. | Moving object recognition systems, moving object recognition programs, and moving object recognition methods |
| CN108573601A (en) * | 2018-03-26 | 2018-09-25 | 同济大学 | A Construction Method of Traffic Safety Risk Field Based on WIM Data |
| CN111243338A (en) * | 2020-02-12 | 2020-06-05 | 南京理工大学 | Collision risk assessment method based on vehicle acceleration |
| CN112767695A (en) * | 2021-01-07 | 2021-05-07 | 哈尔滨工业大学 | Real-time prediction method and system for traffic accident risk at signalized intersection |
| CN113112809A (en) * | 2021-04-23 | 2021-07-13 | 武汉理工大学 | Intersection traffic safety risk evaluation system based on holographic sensing |
| CN113593273A (en) * | 2021-07-22 | 2021-11-02 | 吉林大学 | No-signal control road intersection collision early warning method based on V2I communication |
| WO2021226059A1 (en) * | 2020-05-04 | 2021-11-11 | Intel Corporation | Generation and transmission of vulnerable road user awareness messages |
-
2022
- 2022-04-08 CN CN202210366574.5A patent/CN114882699B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2693416A2 (en) * | 2012-07-31 | 2014-02-05 | Denso IT Laboratory, Inc. | Moving object recognition systems, moving object recognition programs, and moving object recognition methods |
| CN108573601A (en) * | 2018-03-26 | 2018-09-25 | 同济大学 | A Construction Method of Traffic Safety Risk Field Based on WIM Data |
| CN111243338A (en) * | 2020-02-12 | 2020-06-05 | 南京理工大学 | Collision risk assessment method based on vehicle acceleration |
| WO2021226059A1 (en) * | 2020-05-04 | 2021-11-11 | Intel Corporation | Generation and transmission of vulnerable road user awareness messages |
| CN112767695A (en) * | 2021-01-07 | 2021-05-07 | 哈尔滨工业大学 | Real-time prediction method and system for traffic accident risk at signalized intersection |
| CN113112809A (en) * | 2021-04-23 | 2021-07-13 | 武汉理工大学 | Intersection traffic safety risk evaluation system based on holographic sensing |
| CN113593273A (en) * | 2021-07-22 | 2021-11-02 | 吉林大学 | No-signal control road intersection collision early warning method based on V2I communication |
Non-Patent Citations (2)
| Title |
|---|
| Evaluating the Driving Risk of Near-Crash Events Using a Mixed-Ordered Logit Model;Hasan. A. H. Naji, Qingji Xue, Nengchao Lyu 2, Chaozhong Wu and Ke Zheng;Sustainability;第10卷(第8期);1~20 * |
| 基于视频识别的互通合流区交通冲突空间分布;赵笑月，汪攀，朱顺应，蒋若曦，邹禾;公路交通科技;第38卷(第5期);90~99 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114882699A (en) | 2022-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111489588B (en) | Vehicle driving risk early warning method and device, equipment and storage medium | |
| CN104217590B (en) | Method for making the electronic controller in main vehicle determine traffic density | |
| US9524643B2 (en) | Orientation sensitive traffic collision warning system | |
| US10032085B2 (en) | Method and system to identify traffic lights by an autonomous vehicle | |
| CN106240458B (en) | A kind of vehicular frontal impact method for early warning based on vehicle-mounted binocular camera | |
| CN113744563B (en) | A real-time road-vehicle risk estimation method based on trajectory data | |
| US11003925B2 (en) | Event prediction system, event prediction method, program, and recording medium having same recorded therein | |
| CN112172663A (en) | Danger alarm method based on door opening and related equipment | |
| CN113060131B (en) | Obstacle map generation method and device, vehicle and storage medium | |
| CN113815620B (en) | Method, device and equipment for evaluating safe driving of vehicle and storage medium | |
| CN117557600B (en) | Vehicle-mounted image processing method and system | |
| CN114882699B (en) | Road section traffic risk identification method based on conflict space-time correlation characteristics in area | |
| CN115056773B (en) | Pedestrian micro-collision recognition method and system in low-speed scene | |
| CN118609368A (en) | A method, device and medium for intelligent control of tunnel traffic based on holographic perception | |
| CN119314336B (en) | Potential traffic safety analysis method, device, electronic device and storage medium | |
| CN116630891A (en) | Traffic abnormal event detection system and method | |
| CN119348624A (en) | Obstacle perception method for industrial vehicle ADAS based on large model | |
| CN105730330B (en) | Driving safety system and barrier screening method thereof | |
| CN116985787A (en) | Vehicle running control method, device, equipment and storage medium | |
| CN117173652A (en) | Blind area detection method, alarm method, device, vehicle, medium and equipment | |
| US20230154312A1 (en) | State estimation method, state estimation apparatus and program | |
| CN114167406B (en) | System for reducing false alarm of radar through fusion | |
| CN120116972A (en) | Vehicle-mounted safety alarm system | |
| CN118248004B (en) | Road real-time collision risk assessment method based on road side millimeter wave traffic radar | |
| Sukegawa et al. | Estimation of Drivers' Cognitive Load Through Foot Placement Analysis in a Car-Sharing Service |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |